@inproceedings{bao-etal-2026-language,
title = "Language Models Should Be Used to Surface the Unwritten Code of Science",
author = "Bao, Honglin and
Wu, Siyang and
Choi, Jiwoong and
Mao, Yingrong and
Evans, James",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.103/",
pages = "2264--2289",
ISBN = "979-8-89176-439-2",
abstract = "This position paper argues that researchers should not only study how human biases enter large language models (LLMs), but actively leverage those biases as diagnostic tools to surface society{'}s ``unwritten code''{---}the tacit norms and hidden heuristics that govern high-stakes decisions yet resist explicit articulation. We present a case study in peer review: a framework that iteratively pushes LLMs to generate self-consistent hypotheses explaining score differences across 26,731 submissions to 46 conferences. LLMs' normative priors (cues extracted by self-talk) emphasizing theoretical rigor are systematically updated toward posteriors (cues actually used in the judgment) emphasizing storytelling and contextualization{---}a finding cross-validated by independent human survey evidence. Human reviewers explicitly reward prior-aligned aspects (r=0.49) but rarely articulate the storytelling posteriors (r=-0.14), despite implicitly rewarding them. These findings generalize to out-of-sample judgment and different models. We argue this framework applies to hiring, admissions, and criminal justice, offering a scalable path to making hidden evaluative codes visible for public scrutiny and equitable reform."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bao-etal-2026-language">
<titleInfo>
<title>Language Models Should Be Used to Surface the Unwritten Code of Science</title>
</titleInfo>
<name type="personal">
<namePart type="given">Honglin</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siyang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiwoong</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingrong</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Evans</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>This position paper argues that researchers should not only study how human biases enter large language models (LLMs), but actively leverage those biases as diagnostic tools to surface society’s “unwritten code”—the tacit norms and hidden heuristics that govern high-stakes decisions yet resist explicit articulation. We present a case study in peer review: a framework that iteratively pushes LLMs to generate self-consistent hypotheses explaining score differences across 26,731 submissions to 46 conferences. LLMs’ normative priors (cues extracted by self-talk) emphasizing theoretical rigor are systematically updated toward posteriors (cues actually used in the judgment) emphasizing storytelling and contextualization—a finding cross-validated by independent human survey evidence. Human reviewers explicitly reward prior-aligned aspects (r=0.49) but rarely articulate the storytelling posteriors (r=-0.14), despite implicitly rewarding them. These findings generalize to out-of-sample judgment and different models. We argue this framework applies to hiring, admissions, and criminal justice, offering a scalable path to making hidden evaluative codes visible for public scrutiny and equitable reform.</abstract>
<identifier type="citekey">bao-etal-2026-language</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.103/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>2264</start>
<end>2289</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Models Should Be Used to Surface the Unwritten Code of Science
%A Bao, Honglin
%A Wu, Siyang
%A Choi, Jiwoong
%A Mao, Yingrong
%A Evans, James
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F bao-etal-2026-language
%X This position paper argues that researchers should not only study how human biases enter large language models (LLMs), but actively leverage those biases as diagnostic tools to surface society’s “unwritten code”—the tacit norms and hidden heuristics that govern high-stakes decisions yet resist explicit articulation. We present a case study in peer review: a framework that iteratively pushes LLMs to generate self-consistent hypotheses explaining score differences across 26,731 submissions to 46 conferences. LLMs’ normative priors (cues extracted by self-talk) emphasizing theoretical rigor are systematically updated toward posteriors (cues actually used in the judgment) emphasizing storytelling and contextualization—a finding cross-validated by independent human survey evidence. Human reviewers explicitly reward prior-aligned aspects (r=0.49) but rarely articulate the storytelling posteriors (r=-0.14), despite implicitly rewarding them. These findings generalize to out-of-sample judgment and different models. We argue this framework applies to hiring, admissions, and criminal justice, offering a scalable path to making hidden evaluative codes visible for public scrutiny and equitable reform.
%U https://aclanthology.org/2026.aacl-long.103/
%P 2264-2289
Markdown (Informal)
[Language Models Should Be Used to Surface the Unwritten Code of Science](https://aclanthology.org/2026.aacl-long.103/) (Bao et al., AACL-IJCNLP 2026)
ACL
- Honglin Bao, Siyang Wu, Jiwoong Choi, Yingrong Mao, and James Evans. 2026. Language Models Should Be Used to Surface the Unwritten Code of Science. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2264–2289, Hengqin, China. Association for Computational Linguistics.